List your company

Molecule Correction on ChEBI-20

71.66BLEU ScoreAMREC
37.828846.611955.39564.1781Jun 4, 2026

Evaluation results

MethodLinks
AMRECBackbone=GPT-5.4-mini, Tool-augmented=false2026.0671.6686.6167.9657.619.5980.0731.25267.451
AMRECBackbone=Claude-haiku-4.5, Tool-augmented=false2026.0670.8885.7763.4754.0816.8979.1720.32435.1682
AMRECBackbone=Gemini-3.1-Flash-Lite, Tool-augmented=false2026.0669.8886.1863.2257.4524.2979.1523.52149.8556
ReAct-TBackbone=Gemini-3.1-Flash-Lite, Tool-augmented=true2026.0668.4284.4364.855.9419.2978.823.857.3022
ReWOO-TBackbone=Claude-haiku-4.5, Tool-augmented=true2026.0666.1983.6258.9449.5914.1975.7622.35145.6864
ReWOOBackbone=Gemini-3.1-Flash-Lite, Tool-augmented=false2026.0665.4384.4261.0353.6823.5775.727.258.8451
PlanAndAct-TBackbone=Claude-haiku-4.5, Tool-augmented=true2026.0664.7980.9659.4248.639.4675.3722.55.7312
ReWOO-TBackbone=Gemini-3.1-Flash-Lite, Tool-augmented=true2026.0664.7784.0259.553.7922.1475.527.71438.7526
PlanAndAct-TBackbone=Gemini-3.1-Flash-Lite, Tool-augmented=true2026.0664.3780.4160.0950.8312.8676.1225.09298.3742
ReAct-TBackbone=Claude-haiku-4.5, Tool-augmented=true2026.0664.2880.8857.5848.1410.1475.4422.54735.9749
Initial RawBackbone=GPT-5.4-mini, Tool-augmented=false2026.0664.07————72.4746.4433—
ReAct-TBackbone=GPT-5.4-mini, Tool-augmented=true2026.0663.8380.7962.7649.159.7974.8936.72168.841
Initial RawBackbone=Gemini-3.1-Flash-Lite, Tool-augmented=false2026.0663.57————75.5525.2214—
Initial RawBackbone=Claude-haiku-4.5, Tool-augmented=false2026.0663.28————74.3924.5405—
ReWOO-TBackbone=GPT-5.4-mini, Tool-augmented=true2026.0662.1481.5256.7245.0911.3473.8335.835110.355
ReWOOBackbone=GPT-5.4-mini, Tool-augmented=false2026.0662.0782.7458.8147.7414.9574.2736.788711.3297
PlanAndAct-TBackbone=GPT-5.4-mini, Tool-augmented=true2026.0661.7380.8260.7947.897.7373.9739.90218.4538
ReWOOBackbone=Claude-haiku-4.5, Tool-augmented=false2026.0661.7380.8553.3745.1413.5174.2723.82437.2375
ReActBackbone=Claude-haiku-4.5, Tool-augmented=false2026.0659.0278.8652.1543.4610.1472.0224.86497.7959
PlanAndActBackbone=Gemini-3.1-Flash-Lite, Tool-augmented=false2026.0658.9179.1852.7544.1411.4373.0530.478610.5412
ReActBackbone=Gemini-3.1-Flash-Lite, Tool-augmented=false2026.0658.4179.5551.9344.7217.1471.6129.5510.7484
LLM-CorrectorBackbone=Gemini-3.1-Flash-Lite, Tool-augmented=false2026.0656.5879.0249.0641.6412.1470.5834.721412.9917
ReActBackbone=GPT-5.4-mini, Tool-augmented=false2026.0655.7477.6648.7338.235.1569.5441.793813.087
PlanAndActBackbone=GPT-5.4-mini, Tool-augmented=false2026.0655.1677.748.8238.026.1969.4548.371112.6822
PlanAndActBackbone=Claude-haiku-4.5, Tool-augmented=false2026.0654.4176.0746.2638.36.0869.8725.72979.056
LLM-CorrectorBackbone=GPT-5.4-mini, Tool-augmented=false2026.0649.7975.0544.0732.395.6765.4749.994814.7324
SMISELFBackbone=GPT-5.4-mini, Tool-augmented=false2026.0644.6771.5437.0826.28062.9550.881418.4483
SMISELFBackbone=Claude-haiku-4.5, Tool-augmented=false2026.0643.2669.237.8827.62.0362.2629.770313.7593
SMISELFBackbone=Gemini-3.1-Flash-Lite, Tool-augmented=false2026.0642.4769.3234.9327.292.1461.7234.118.3432
LLM-CorrectorBackbone=Claude-haiku-4.5, Tool-augmented=false2026.0639.1357.0436.6228.976.7652.1338.378418.8859